Log analysis shows adaptive condition concentrates practice on unmastered concepts while random condition over-practices easy ones¶
Claim · All claims
Evidence · 1 study · causalr1·q2
Currency · newest study 2024 · checked against its sources 2026-10-28 (automated, 1 of 1 entry) · not reviewed by a person
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? In the adaptive condition over 80% of group-by-task sequences ended in mastery versus 16.7% in the random condition. → Yannier 2024
Evidence¶
Yannier 2024¶
Yannier, N., Hudson, S. E., Chang, H., & Koedinger, K. R. (2024). AI Adaptivity in a Mixed-Reality System Improves Learning. International Journal of Artificial Intelligence in Education, 34, 1541–1558. https://doi.org/10.1007/s40593-023-00388-5
q2 · i? · causal · r1
Log-file analysis of the same 18 pairs; Table 2 reports adaptive 80.5% mastered, 0.0% over-practiced, 19.5% unmastered versus random 16.7%, 27.8%, 55.5%.
"In the Adaptive condition, over 80% of the 36 group-by-task sequences end in mastery. No Adaptive condition sequences involve over-practice (though some get some extra practice after mastering all four tasks). In contrast, in the Random condition, only 16.7% of the 36 group-by-task sequences end in mastery."
Discussion¶
Related Claims¶
- LMS process indicators documented adaptive engagement during the eight-week intervention, with most experimental students reaching mastery by unit end — related
- Adaptive scaffolding policies (BKT and DRL) significantly improve posttest performance over a non-adaptive control in a logic ITS — related
- Adaptive spaced retrieval practice produced higher end-of-semester posttest performance than learner-directed AI study, but fixed spaced retrieval did not significantly outperform learner-directed study — related
- Students in the non-adaptive condition reached significantly higher average mastery probabilities than students in the adaptive condition — reports the opposite
- BKT adaptivity in a mixed-reality Intelligent Science Station improves children's post-test learning of scientific principles compared to random task selection — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
bkt-adaptivity-log-practice-allocation |
title |
Log analysis shows adaptive condition concentrates practice on unmastered concepts while random condition over-practices easy ones |
description |
Log analysis shows adaptive condition concentrates practice on unmastered concepts while random condition over-practices easy ones |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2024 |
source_checked |
2026-10-28 |
generated |
by process:wiki-ingest on 2026-10-28 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — yannier-2024 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.